Upstream/feature/add xiaomi mimo

dev/null/post-checkout

@@ -0,0 +1,3 @@
+#!/bin/sh
+command -v git-lfs >/dev/null 2>&1 || { printf >&2 "\n%s\n\n" "This repository is configured for Git LFS but 'git-lfs' was not found on your path. If you no longer wish to use Git LFS, remove this hook by deleting the 'post-checkout' file in the hooks directory (set by 'core.hookspath'; usually '.git/hooks')."; exit 2; }
+git lfs post-checkout "$@"

dev/null/post-commit

@@ -0,0 +1,3 @@
+#!/bin/sh
+command -v git-lfs >/dev/null 2>&1 || { printf >&2 "\n%s\n\n" "This repository is configured for Git LFS but 'git-lfs' was not found on your path. If you no longer wish to use Git LFS, remove this hook by deleting the 'post-commit' file in the hooks directory (set by 'core.hookspath'; usually '.git/hooks')."; exit 2; }
+git lfs post-commit "$@"

dev/null/post-merge

@@ -0,0 +1,3 @@
+#!/bin/sh
+command -v git-lfs >/dev/null 2>&1 || { printf >&2 "\n%s\n\n" "This repository is configured for Git LFS but 'git-lfs' was not found on your path. If you no longer wish to use Git LFS, remove this hook by deleting the 'post-merge' file in the hooks directory (set by 'core.hookspath'; usually '.git/hooks')."; exit 2; }
+git lfs post-merge "$@"

dev/null/pre-push

@@ -0,0 +1,3 @@
+#!/bin/sh
+command -v git-lfs >/dev/null 2>&1 || { printf >&2 "\n%s\n\n" "This repository is configured for Git LFS but 'git-lfs' was not found on your path. If you no longer wish to use Git LFS, remove this hook by deleting the 'pre-push' file in the hooks directory (set by 'core.hookspath'; usually '.git/hooks')."; exit 2; }
+git lfs pre-push "$@"

packages/types/src/provider-settings.ts

@@ -20,6 +20,7 @@ import {
 	xaiModels,
 	internationalZAiModels,
 	minimaxModels,
+	mimoModels,
 } from "./providers/index.js"
 
 /**
@@ -121,6 +122,7 @@ export const providerNames = [
 	"mistral",
 	"moonshot",
 	"minimax",
+	"mimo",
 	"openai-codex",
 	"openai-native",
 	"qwen-code",
@@ -334,6 +336,18 @@ const minimaxSchema = apiModelIdProviderModelSchema.extend({
 	minimaxApiKey: z.string().optional(),
 })
 
+const mimoSchema = apiModelIdProviderModelSchema.extend({
+	mimoBaseUrl: z
+		.union([
+			z.literal("https://api.xiaomimimo.com/v1"),
+			z.literal("https://token-plan-cn.xiaomimimo.com/v1"),
+			z.literal("https://token-plan-sgp.xiaomimimo.com/v1"),
+			z.literal("https://token-plan-ams.xiaomimimo.com/v1"),
+		])
+		.optional(),
+	mimoApiKey: z.string().optional(),
+})
+
 const requestySchema = baseProviderSettingsSchema.extend({
 	requestyBaseUrl: z.string().optional(),
 	requestyApiKey: z.string().optional(),
@@ -417,6 +431,7 @@ export const providerSettingsSchemaDiscriminated = z.discriminatedUnion("apiProv
 	poeSchema.merge(z.object({ apiProvider: z.literal("poe") })),
 	moonshotSchema.merge(z.object({ apiProvider: z.literal("moonshot") })),
 	minimaxSchema.merge(z.object({ apiProvider: z.literal("minimax") })),
+	mimoSchema.merge(z.object({ apiProvider: z.literal("mimo") })),
 	requestySchema.merge(z.object({ apiProvider: z.literal("requesty") })),
 	unboundSchema.merge(z.object({ apiProvider: z.literal("unbound") })),
 	fakeAiSchema.merge(z.object({ apiProvider: z.literal("fake-ai") })),
@@ -451,6 +466,7 @@ export const providerSettingsSchema = z.object({
 	...poeSchema.shape,
 	...moonshotSchema.shape,
 	...minimaxSchema.shape,
+	...mimoSchema.shape,
 	...requestySchema.shape,
 	...unboundSchema.shape,
 	...fakeAiSchema.shape,
@@ -525,6 +541,7 @@ export const modelIdKeysByProvider: Record<TypicalProvider, ModelIdKey> = {
 	mistral: "apiModelId",
 	moonshot: "apiModelId",
 	minimax: "apiModelId",
+	mimo: "apiModelId",
 	deepseek: "apiModelId",
 	poe: "apiModelId",
 	"qwen-code": "apiModelId",
@@ -617,6 +634,11 @@ export const MODELS_BY_PROVIDER: Record<
 		label: "MiniMax",
 		models: Object.keys(minimaxModels),
 	},
+	mimo: {
+		id: "mimo",
+		label: "Xiaomi MiMo",
+		models: Object.keys(mimoModels),
+	},
 	"openai-codex": {
 		id: "openai-codex",
 		label: "OpenAI - ChatGPT Plus/Pro",

packages/types/src/providers/index.ts

@@ -25,6 +25,7 @@ export * from "./xai.js"
 export * from "./vercel-ai-gateway.js"
 export * from "./zai.js"
 export * from "./minimax.js"
+export * from "./mimo.js"
 
 import { anthropicDefaultModelId } from "./anthropic.js"
 import { basetenDefaultModelId } from "./baseten.js"
@@ -49,6 +50,7 @@ import { xaiDefaultModelId } from "./xai.js"
 import { vercelAiGatewayDefaultModelId } from "./vercel-ai-gateway.js"
 import { internationalZAiDefaultModelId, mainlandZAiDefaultModelId } from "./zai.js"
 import { minimaxDefaultModelId } from "./minimax.js"
+import { mimoDefaultModelId } from "./mimo.js"
 
 // Import the ProviderName type from provider-settings to avoid duplication
 import type { ProviderName } from "../provider-settings.js"
@@ -85,6 +87,8 @@ export function getProviderDefaultModelId(
 			return moonshotDefaultModelId
 		case "minimax":
 			return minimaxDefaultModelId
+		case "mimo":
+			return mimoDefaultModelId
 		case "zai":
 			return options?.isChina ? mainlandZAiDefaultModelId : internationalZAiDefaultModelId
 		case "openai-native":

packages/types/src/providers/mimo.ts

@@ -0,0 +1,49 @@
+import type { ModelInfo } from "../model.js"
+
+// https://platform.xiaomimimo.com/static/docs/pricing.md
+export type MimoModelId = keyof typeof mimoModels
+
+export const mimoDefaultModelId: MimoModelId = "mimo-v2.5-pro"
+
+export const mimoModels = {
+	"mimo-v2.5-pro": {
+		maxTokens: 131_072,
+		contextWindow: 1_048_576,
+		supportsImages: false,
+		supportsPromptCache: true,
+		preserveReasoning: true,
+		inputPrice: 1.0, // $1.00 per million tokens (cache miss, ≤256K)
+		outputPrice: 3.0, // $3.00 per million tokens
+		cacheReadsPrice: 0.2, // $0.20 per million tokens (cache hit)
+		cacheWritesPrice: 0, // Free for limited time
+		description:
+			"MiMo V2.5 Pro - Xiaomi's flagship reasoning model with 1M context, interleaved thinking, tool calling, and structured output.",
+	},
+	"mimo-v2.5": {
+		maxTokens: 131_072,
+		contextWindow: 1_048_576,
+		supportsImages: false,
+		supportsPromptCache: true,
+		preserveReasoning: true,
+		inputPrice: 0.4, // $0.40 per million tokens (cache miss, ≤256K)
+		outputPrice: 2.0, // $2.00 per million tokens
+		cacheReadsPrice: 0.08, // $0.08 per million tokens (cache hit)
+		cacheWritesPrice: 0, // Free for limited time
+		description:
+			"MiMo V2.5 - Full modal understanding model with 1M context, deep thinking, tool calling, and structured output.",
+	},
+	"mimo-v2-flash": {
+		maxTokens: 65_536,
+		contextWindow: 262_144,
+		supportsImages: false,
+		supportsPromptCache: false,
+		preserveReasoning: true,
+		inputPrice: 0.1, // $0.10 per million tokens (cache miss)
+		outputPrice: 0.3, // $0.30 per million tokens
+		description: "MiMo V2 Flash - Fast and cost-effective reasoning model with tool calling support.",
+	},
+} as const satisfies Record<string, ModelInfo>
+
+export const mimoDefaultModelInfo: ModelInfo = mimoModels[mimoDefaultModelId]
+
+export const MIMO_DEFAULT_TEMPERATURE = 1.0

src/api/index.ts

@@ -33,6 +33,7 @@ import {
 	FireworksHandler,
 	VercelAiGatewayHandler,
 	MiniMaxHandler,
+	MimoHandler,
 	BasetenHandler,
 } from "./providers"
 import { NativeOllamaHandler } from "./providers/native-ollama"
@@ -167,6 +168,8 @@ export function buildApiHandler(configuration: ProviderSettings): ApiHandler {
 			return new LiteLLMHandler(options)
 		case "sambanova":
 			return new SambaNovaHandler(options)
+		case "mimo":
+			return new MimoHandler(options)
 		case "zai":
 			return new ZAiHandler(options)
 		case "fireworks":

src/api/providers/base-openai-compatible-provider.ts

@@ -90,7 +90,10 @@ export abstract class BaseOpenAiCompatibleProvider<ModelName extends string>
 			model,
 			max_tokens,
 			temperature,
-			messages: [{ role: "system", content: systemPrompt }, ...convertToOpenAiMessages(messages)],
+			messages: [
+				{ role: "system", content: systemPrompt },
+				...convertToOpenAiMessages(messages, { modelId: model }),
+			],
 			stream: true,
 			stream_options: { include_usage: true },
 			tools: this.convertToolsForOpenAI(metadata?.tools),
@@ -224,7 +227,7 @@ export abstract class BaseOpenAiCompatibleProvider<ModelName extends string>
 
 		const params: OpenAI.Chat.Completions.ChatCompletionCreateParams = {
 			model: modelId,
-			messages: [{ role: "user", content: prompt }],
+			messages: [{ role: "user", content: prompt }], // No history, no MiMo strip needed
 		}
 
 		// Add thinking parameter if reasoning is enabled and model supports it

src/api/providers/index.ts

@@ -27,4 +27,5 @@ export { FireworksHandler } from "./fireworks"
 export { RooHandler } from "./roo"
 export { VercelAiGatewayHandler } from "./vercel-ai-gateway"
 export { MiniMaxHandler } from "./minimax"
+export { MimoHandler } from "./mimo"
 export { BasetenHandler } from "./baseten"

src/api/providers/lite-llm.ts

@@ -117,6 +117,7 @@ export class LiteLLMHandler extends RouterProvider implements SingleCompletionHa
 		const { id: modelId, info } = await this.fetchModel()
 
 		const openAiMessages = convertToOpenAiMessages(messages, {
+			modelId,
 			normalizeToolCallId: sanitizeOpenAiCallId,
 		})
 

src/api/providers/lm-studio.ts

@@ -44,7 +44,7 @@ export class LmStudioHandler extends BaseProvider implements SingleCompletionHan
 	): ApiStream {
 		const openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = [
 			{ role: "system", content: systemPrompt },
-			...convertToOpenAiMessages(messages),
+			...convertToOpenAiMessages(messages, { modelId: this.getModel().id }),
 		]
 
 		// -------------------------